label-capture-kmp
Pass
Audited by Gen Agent Trust Hub on Sep 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines patterns for processing data scanned from physical labels (barcodes and text). This creates a surface where untrusted external data is ingested into the application context.
- Ingestion points: Data enters the system via the
onSessionUpdatedandonLabelsScannedlisteners defined inSKILL.mdandreferences/integration.md. - Boundary markers: The skill instructs the agent to use structured
LabelDefinitionobjects and regex patterns to constrain and validate the data being scanned. - Capability inventory: The shared logic handles UI updates and data processing based on the scanned label fields.
- Sanitization: The Scandit SDK parses the raw visual data into structured
CapturedLabelandLabelFieldobjects before the application code interacts with it.
Audit Metadata